Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Accounting > STATS > Flashcards

STATS Flashcards

1
Q

Observational study

A

We observe the behavior or ask people questions as they are going about their day to day lives. Ex. Call people and ask them how often they eat out.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Experiment

A

We impose some treatment on people and then observe their behavior or ask questions. Ex. Give people a drug and then do chemical analysis of their blood.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Confounded variables

A

wo variables where the effect of one on the dependent variable cannot be separated from the effect of the other. Ex. If you take drugs and drink alcohol and then have a car accident, the effect of the drugs vs. the alcohol cannot be separated from each other as the cause of the accident.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Population

A

The set of everything. Ex. All the people in America

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Sample

A

A small group pulled from the population. Ex. Sample 40 voters from the population of America

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Voluntary response sampling

A

People volunteer to give data for a study. Ex. people text to a phone number if they agree with a statement and text to a different one if they disagree

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Convenience sampling

A

Convenience sampling People are selected to be in a sample because of convenience or low expense. Ex. Mall intercepts, or asking the people on the floor of your dorm to fill out a survey.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Bias (1)

A

Bias (1) Systematically favoring a certain outcome from research

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

imple random sampling

A

Label all the people in the population with a number. Have a computer select a set of random numbers in that range. People labeled with the number are selected for the sample. Therefore, every person or sub-group of people has an equal chance of being in the sample.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Stratified sampling

A

First breaking the population into natural segments (called strata) and then using random sampling within the strata. Ex. Radio stations or types of colleges (community colleges, public universities, private universities, stand-alone liberal arts colleges)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Multi stage sampling

A

Basically practicing stratified sampling repeatedly to get to a final sample.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Undercoverage

A

Where some members of the population cannot be selected for the sample. Ex. People without phones if one is collecting data over the phone.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Non response

A

When an individual selected for the sample does not provide information.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Response bias

A

Not answering truthfully when asked question about sensitive subjects. Ex. “How much pot do you smoke”

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Subjects

A

people who are involved in the experiment

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Treatment

A

A unique combination of levels of factors given to a set of subjects

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Placebo Effect

A

When a subject thinks that they are feeling better simply because they are involved in a study. Ex. A subject reports decreased amounts of pain even though he is being give a pill that does not contain any drug in it.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Completely Randomized Design

A

Within an experiment, use random sampling to assign the subjects to the different treatments

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Statistical Significance

A

A finding that is unlikely to be due to random chance alone

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Double Blind Experiment

A

Double Blind Experiment Neither the researcher nor the subject knows who is receiving which treatments in a study.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Random or Stochastic phenomenon

A

The outcome of any one trial is unknown, but after a large number of trials the expected pattern is seen. Ex. Relatively equal number of heads and tails in a large number of tosses or a coin.

22
Q

he pieces of a Probability Model

A

See below: S, event, probability to assign chances of seeing the even occur

23
Q

S

A

Sample space—the set of everything that can happen in a random phenomenon

24
Q

Event

A

The thing of interest in a random phenomenon. Ex. Role an even number on a single roll of a die.

25
Q

Discrete Variable

A

A variable that can only take on a set number of values. Ex. The number of spots on a die or the number of fish in a school

26
Q

Finite Sample Space

A

A way to assign probabilities to a discrete variable.

27
Q

COntinuous variable

A

A variable that has values that continue smoothly on a scale. The numbers (not integers) between 0 and 2.

28
Q

infinite sample variable

A

A way to assign probabilities to ranges of events for a continuous variable.

29
Q

Random Varaible

A
  1. Produces only numbers and 2. Is driven by a random (or stochastic) process. Ex. Count the number of defective products coming from an assembly line.
30
Q

explanatory variable

A

a.k.a independent variable. The thing that we have be different for different individuals in order to measure the association with the response variable. Ex. Amount of exercise(=explanatory) and its effect on weight loss(=response variable).

31
Q

Response variable

A

.k.a. dependent variable. See above

32
Q

Marginal distribution

A

The values for one variable if we ignore the categories of the other variable.

33
Q

what does x bar mean

A

it is the mean (average) of a set of data

34
Q

when do you use n-1 and when do you use n

A

you use n-1 in std dev when you are measuring a sample of a population and n when you are measuring the whole population

35
Q

the greater the _____ the higher the spread

A

Standard deviation

36
Q

the sample size effects what

A

variability the larger the difference in sample size the larger

37
Q

The ____should be used as a measure of ______ when distribution is ______ and free of _______

A

mean center symmetric outliers

38
Q

Simpsons paradox

A

A even though in both good and bad condition you would want to go to hospital a due to the detail in the data and therefore there has been a reversal in going from the aggregate to the detailed level of the data therefore simpsons paradox has occurred

39
Q

If the x variable increases by one unit, what happens to the y variable?

A

it changes by the amount of the slope

40
Q

What amount of the variance in the y variable is explained by its linear relationship with the x variable?

A

SQUARE R!!!!

41
Q

what is the maximum strength of r squarded

A

100%

42
Q

what is residual equation

A

observed minus predicted

43
Q

if the data is scattered along the residual x axis what do you say

A

The regression line is accurate in its predictions on the low side of the x-axis. It is not as
accurate on the high side of the x-axis. Therefore THE ACCURACY OF PREDICTIONS FROM
THE REGRESSION LINE IS NOT CONSISTENT.

44
Q

variance

A

is just sigma/ standard deviation (circle with eyelashes) squared

45
Q

N

A

population size

46
Q

μ

A

mean of a population

47
Q

σ

A

standard deviation of a population

48
Q

when the spread of the standard deviation is _____ it is tighter

A

smaller the lower the number the tighter or stronger the relationship is

49
Q

block design

A

, the experimenter divides subjects into subgroups called blocks, such that the variability within blocks is less than the variability between blocks. Then, subjects within each block are randomly assigned to treatment conditions.

50
Q

matched pairs design

A

It can be used when the experiment has only two treatment conditions; and subjects can be grouped into pairs, based on some blocking variable. Then, within each pair, subjects are randomly assigned to different treatments.

51
Q

levels

A

Each factor has two or more levels, i.e., different values of the factor. Combinations of factor levels are called treatments.

52
Q

generalizeability

A

is the ability to reproduce the experiment

Accounting (19 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions